Method, device and equipment for measuring maximum available power of wind farm and storage medium

Abstract

The application provides a wind farm maximum available power calculation method, device, equipment and storage medium, which can be used in the field of wind power generation. The method comprises the following steps: obtaining the characteristic information of a plurality of wind turbine generators in a target wind farm, and constructing a characteristic vector of each wind turbine generator based on the characteristic information; clustering the wind turbine generators according to the characteristic vectors of the wind turbine generators to obtain a plurality of cluster groups; determining the number of wind turbine generators in each cluster group and a sample wind turbine generator, and obtaining the maximum power generated by the sample wind turbine generator in a free power generation mode; for each cluster group, obtaining the calculated power of the cluster group based on the product of the number of wind turbine generators and the maximum power; and obtaining the maximum available power of the target wind farm based on the sum of the calculated power of each cluster group. The method of the application effectively improves the accuracy of the calculation of the maximum available power of the wind farm, and further improves the economy and safety of the operation of the wind farm.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and in particular to a method, apparatus, equipment and storage medium for calculating the maximum generating power of a wind farm. Background Technology

[0002] Wind power generation is a technology that converts the kinetic energy of wind into electrical energy. Because wind energy is a clean and pollution-free renewable energy source, wind power generation does not require the use of fuel and does not produce radiation or air pollution. It is considered an environmentally friendly and renewable energy source.

[0003] Due to limitations in grid transmission capacity and electricity demand, wind farms are currently generally under curtailment. This means that the power generation of wind turbines within the wind farm is limited by the wind farm's control system to ensure the balance of power supply and demand. Therefore, the generators within the wind farm are operated at a set power output to limit the wind farm's power generation and meet grid demand.

[0004] The maximum generating capacity of a wind farm is a crucial data point affecting the power distribution of wind turbines within the farm. The control system needs to use the maximum generating capacity as a reference to allocate the generating power of the wind turbines within the wind farm. If the maximum generating capacity is not accurately calculated, the power parameters allocated to the wind turbines will also be inaccurate. This will prevent the control system from accurately setting the set generating capacity of the wind turbines, leading to unbalanced and unreasonable power distribution within the wind farm, resulting in economic losses for the wind farm and mechanical losses to the wind turbines. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for calculating the maximum generating power of a wind farm, in order to solve the technical problem of low accuracy in the calculation of the maximum generating power of existing wind farms.

[0006] According to the first aspect disclosed in this application, this application provides a method for calculating the maximum generating power of a wind farm, including:

[0007] The feature information of multiple wind turbines within the target wind farm is obtained, and feature vectors of each wind turbine are constructed based on the feature information; wherein, the feature information includes turbine model, power curve, wind condition information and geographical location information;

[0008] Based on the feature vectors of each wind turbine, the wind turbines are clustered to obtain multiple turbine clusters;

[0009] For each turbine cluster, the number of turbines in the cluster and the model turbine are determined, and the maximum power generation of the model turbine in the free power generation mode is obtained; wherein, the model turbine is the wind turbine in the cluster that has the shortest feature distance to the cluster center of the cluster.

[0010] For each cluster of generating units, the calculated power generation of the cluster is obtained based on the product of the number of generating units and the maximum power generation.

[0011] The maximum generating power of the target wind farm is obtained by summing the calculated generating power of each unit cluster.

[0012] In one feasible implementation, the wind turbines are clustered based on their feature vectors to obtain multiple turbine clusters, including:

[0013] Based on the feature vectors of each wind turbine, multiple cluster centers are determined.

[0014] For each wind turbine, the characteristic distance from the wind turbine to each cluster center is obtained, and the wind turbine is assigned to the cluster to which the cluster center corresponding to the shortest characteristic distance belongs;

[0015] For each wind turbine cluster, the mean feature value of the feature vector of each wind turbine in the cluster is calculated, and the cluster center of the cluster is updated with the mean feature value.

[0016] The process then proceeds to obtaining the characteristic distances from each wind turbine to each cluster center, and assigning each wind turbine to the cluster of the cluster center corresponding to the shortest characteristic distance. This process is iterated until convergence, resulting in multiple wind turbine clusters.

[0017] In one feasible implementation, multiple cluster centers are determined based on the feature vectors of each wind turbine, including:

[0018] Randomly select any wind turbine in the target wind farm as the initial cluster center;

[0019] Determine the current cluster center; wherein, the initial current cluster center is the initial cluster center;

[0020] Based on the characteristic distance between each remaining unit and the current cluster center, the distribution probability of each remaining unit being selected as the next cluster center is determined, and the remaining unit corresponding to the maximum distribution probability is selected as the next cluster center; wherein, the remaining units are the other wind turbine units in the target wind farm other than the cluster center;

[0021] The current cluster center is updated as the next cluster center, and the process proceeds to the step of iteratively searching to determine the distribution probability of each remaining unit being selected as the next cluster center based on the feature distance between each remaining unit and the current cluster center, and selecting the remaining unit corresponding to the maximum distribution probability as the next cluster center, in order to determine multiple cluster centers.

[0022] In one feasible implementation, the feature distance satisfies the following formula:

[0023]

[0024] Where d(x) i ,μ k ) represents the eigenvector x of the i-th wind turbine. i The eigenvector μ of the k-th cluster center k The characteristic distance between them, x ij μ represents the j-th component in the eigenvector of the i-th wind turbine. kj Let d represent the j-th component in the eigenvector of the k-th cluster center, and d represent the number of components in the eigenvector.

[0025] In one feasible implementation, the probability distribution satisfies the following formula:

[0026]

[0027] Where P(i) represents the probability distribution of the i-th remaining unit being selected as the next cluster center, and d(x i ,μ k ) represents the feature vector x of the i-th remaining unit. i The eigenvector μ of the k-th cluster center k The feature distance between them, d(x) j ,μ k ) represents the feature vector x of the j-th remaining unit. j The eigenvector μ of the k-th cluster center k The characteristic distance between them, where n represents the number of remaining units.

[0028] In one feasible implementation, the method further includes:

[0029] The actual generating power of the target wind farm is obtained by summing the actual generating power of each wind turbine in the target wind farm.

[0030] Calculate the cumulative root mean square error between the actual transmittable power and the maximum transmittable power;

[0031] If the cumulative root mean square error is greater than a preset error threshold, the process proceeds to the step of acquiring feature information of multiple wind turbines in the target wind farm and constructing feature vectors for each wind turbine based on the feature information.

[0032] In one feasible implementation, the cumulative root mean square error satisfies the following formula:

[0033]

[0034] Among them, P e This represents the cumulative root mean square error, where K represents the number of unit clusters, and m k P represents the number of units in the k-th unit cluster. k This represents the maximum generating capacity of the model unit in the k-th unit cluster. This represents the actual power generation of the l-th wind turbine in the k-th turbine cluster.

[0035] According to the second aspect disclosed in this application, this application provides a device for calculating the maximum generating power of a wind farm, comprising:

[0036] The feature acquisition module is used to acquire feature information of multiple wind turbines within the target wind farm and construct feature vectors for each wind turbine based on the feature information; wherein, the feature information includes turbine model, power curve, wind condition information and geographical location information;

[0037] The unit clustering module is used to cluster the wind turbines according to the feature vectors of each wind turbine to obtain multiple unit clusters;

[0038] The template selection module is used to determine the number of units and the template unit for each unit cluster, and to obtain the maximum power generation of the template unit in the free power generation mode; wherein, the template unit is the wind turbine unit in the unit cluster that has the shortest feature distance to the cluster center of the unit cluster.

[0039] The power calculation module is used to obtain the calculated power generation of each unit cluster based on the product of the number of units and the maximum power generation.

[0040] The power calculation module is used to obtain the maximum generating power of the target wind farm by summing the measured generating power of each unit cluster.

[0041] According to a third aspect disclosed in this application, an electronic device is provided, including a processor and a memory communicatively connected to the processor;

[0042] The memory stores computer-executed instructions;

[0043] The processor executes computer execution instructions stored in the memory to implement the method described in any one of the first aspects.

[0044] According to a fourth aspect disclosed in this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, are used to implement the method described in any one of the first aspects.

[0045] According to the fifth aspect disclosed in this application, a computer program product is provided, comprising a computer program that, when executed by a processor, is used to implement the method described in any one of the first aspects.

[0046] Compared with the prior art, this application has the following advantages:

[0047] This application provides a method, apparatus, equipment, and storage medium for calculating the maximum generating power of a wind farm. It comprehensively considers the characteristics of each wind turbine within the wind farm, including its model, power, wind conditions, and geographical location. This clusters wind turbines with similar characteristics into multiple turbine clusters. A representative turbine is then selected from each cluster to calculate the generating power of the cluster, ultimately yielding the maximum generating power of the entire wind farm. By clustering the wind turbines, the selection of representative turbines becomes more representative, leading to more accurate calculations of the maximum generating power based on these turbines. This significantly improves the accuracy of the maximum generating power calculation. The increased accuracy of the maximum generating power facilitates the specification of power allocation and scheduling strategies for wind turbines within the wind farm by the control system, thereby enhancing the economic efficiency and safety of wind farm operation. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] Figure 1 A flowchart illustrating a method for calculating the maximum generating power of a wind farm, provided in an embodiment of this application;

[0050] Figure 2 A flowchart illustrating another method for calculating the maximum generating power of a wind farm provided in this application embodiment;

[0051] Figure 3 A schematic diagram of a wind farm maximum generating power calculation device provided in this application embodiment;

[0052] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0053] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0055] Before providing a further detailed description of the embodiments of this application, the nouns and terms used in the embodiments of this application will be explained first. The nouns and terms used in the embodiments of this application shall be interpreted as follows:

[0056] Maximum generating capacity, also known as theoretical generating capacity, is the upper limit of electricity output that wind turbines in a wind farm can produce, influenced by both natural conditions and their mechanical structure. This means that the amount of electricity a wind turbine can generate varies under different wind speeds. A wind farm contains multiple wind turbines located in different geographical locations, leading to varying wind speeds and thus different power outputs for each turbine. Therefore, to calculate the maximum generating capacity of the entire wind farm, it is necessary to accurately measure the generating capacity of each wind turbine within the farm.

[0057] Power point tracking (PPT) mode refers to a power generation mode in which wind turbines operate at a set power output. In this mode, the output power of the wind turbine is set within a specific range by the control system to ensure the stable operation of the power system. This typically involves precise control of parameters such as the blade speed and blade angle of the wind turbine to achieve precise adjustment of the output power.

[0058] Free generation mode refers to a power generation mode that allows wind turbines to autonomously adjust according to real-time wind speed and direction conditions in order to capture wind energy and convert it into electrical energy to the maximum extent.

[0059] Wind power generation is a technology that converts the kinetic energy of wind into electrical energy. Because wind energy is a clean and pollution-free renewable energy source, wind power generation does not require the use of fuel and does not produce radiation or air pollution. It is considered an environmentally friendly and renewable energy source.

[0060] Due to limitations in grid transmission capacity and electricity demand, wind farms are currently generally under curtailment. This means that the power generation of wind turbines within the wind farm is limited by the wind farm's control system to ensure the balance of power supply and demand. Therefore, the generators within the wind farm are operated at a set power output to limit the wind farm's power generation and meet grid demand.

[0061] The maximum generating capacity of a wind farm is a crucial data point affecting the power distribution of wind turbines within the farm. The control system needs to use the maximum generating capacity as a reference to allocate the generating power of the wind turbines within the wind farm. If the maximum generating capacity is not accurately calculated, the power parameters allocated to the wind turbines will also be inaccurate. This will prevent the control system from accurately setting the set generating capacity of the wind turbines, leading to unbalanced and unreasonable power distribution within the wind farm, resulting in economic losses for the wind farm and mechanical losses to the wind turbines.

[0062] This is because wind turbines typically reduce their power output by adjusting the blade pitch angle. Prolonged low-power operation can cause mechanical damage or load issues, negatively impacting the turbine's lifespan. Suppressing wind turbine operation can also lead to safety problems. Therefore, the upper-level control system needs to optimize the power control of the wind turbines, which requires the use of the maximum allowable power output. For example, the maximum allowable power output can be used as a constraint for power allocation optimization, making it a necessary data point. If the maximum allowable power output is not accurately calculated, the power parameters allocated to the wind turbines will also be inaccurate, preventing the control system from accurately setting the turbines' power output and resulting in errors in the optimization results.

[0063] Currently, under power curtailment conditions, most wind turbines in wind farms operate in power point tracking (PPT) mode, which limits the wind farm's power generation by setting a fixed power output to meet the power system's supply and demand balance. Since the wind turbines generate electricity at a fixed power level, it's impossible to obtain the wind farm's maximum usable power output from the actual power generated by the turbines. Therefore, in existing technologies, a model turbine is selected in the wind farm and controlled to generate electricity freely in a free-generation mode. The maximum generating capacity of the wind farm is estimated by using the maximum generating capacity of the model turbine and the number of turbines it represents. For example, for wind turbines located on an uphill slope, a model turbine is selected, and the maximum generating capacity of multiple wind turbines on the hillside is obtained by multiplying the maximum generating capacity of the model turbine in free-generation mode by the number of wind turbines on the hillside. For wind turbines located at the foot of the hill, a model turbine is selected, and the maximum generating capacity of multiple wind turbines at the foot of the hill is obtained by multiplying the maximum generating capacity of the model turbine in free-generation mode by the number of wind turbines at the foot of the hill. Finally, the maximum generating capacity of the wind turbines on the hillside and at the foot of the hill is added together to obtain the maximum generating capacity of the entire wind farm. However, in existing technologies, prototype wind turbines are generally selected manually. This manual selection relies on the experience of the staff for simple selection. The number of prototype wind turbines, which area they can represent, and how many wind turbines they can represent are all determined by manual experience. This can lead to the prototype wind turbines not accurately reflecting the power generation status of other wind turbines in the wind farm, resulting in a large error in the final calculated maximum power output, which cannot meet actual needs.

[0064] Because wind turbines operate in power point tracking (PPT) mode, the upper-level control system of the wind farm issues a PPT command value to each wind turbine. The set power output in this command value is calculated based on the wind farm's maximum allowable power output. For example, if the allocated power value exceeds the wind turbine's actual power output due to an error in the maximum allowable power output, it exceeds the wind turbine's capacity, resulting in abnormal power allocation. If the wind turbine's actual power output matches the designated power output, the wind turbine's power generation capacity can be maximized, thus maximizing the wind farm's economic benefits.

[0065] To address the aforementioned technical issues, this application proposes a method for calculating the maximum generating power of a wind farm. This method involves clustering wind turbine units with similar characteristics within the wind farm into a unit cluster, then selecting a more representative sample unit to calculate the generating power of the unit cluster, and further obtaining the calculated value of the maximum generating power of the entire wind farm. This effectively improves the accuracy of the calculation results for the maximum generating power of the wind farm.

[0066] The technical solution of the wind farm maximum generating power calculation method provided in this application will be described in detail below through specific embodiments. It should be noted that the following embodiments may exist alone or in combination with each other, and the same or similar content may not be described again in different embodiments.

[0067] It should be noted that the execution entity of the wind farm maximum generating power calculation method provided in this application embodiment is the wind farm's control system, and correspondingly, the wind farm maximum generating power calculation device is also installed in the control system. Specifically, the control system is used for the optimized control and management of the wind farm, and generally includes equipment such as a central controller, sensors, and actuators.

[0068] Figure 1 A flowchart illustrating a method for calculating the maximum generating power of a wind farm, as provided in this application embodiment, is shown below. Figure 1 In some embodiments, the method for calculating the maximum generating power of a wind farm includes the following steps:

[0069] S101, acquire the feature information of multiple wind turbine units in the target wind farm, and construct the feature vector of each wind turbine unit based on the feature information; wherein, the feature information includes the unit model, wind condition information, power curve and geographical location information.

[0070] This involves collecting relevant feature information that affects the power generation efficiency of wind turbines and using this information to construct feature vectors for wind turbines. This allows for subsequent clustering of wind turbines based on these feature vectors, grouping wind turbines with similar features into the same cluster to form multiple clusters.

[0071] Specifically, the model number of the wind turbine is determined by the type and capacity of the wind turbine, in order to classify the wind turbines.

[0072] Specifically, wind condition information includes wind speed and direction. Wind turbines work by using wind power to rotate the turbine blades, which in turn increases the rotational speed via a speed increaser, causing the generator to produce electricity. Therefore, wind conditions are a crucial factor affecting the power generation efficiency of wind turbines. Wind speed directly determines the rotational speed of the turbine blades, thus affecting the amount of electricity generated. Therefore, changes in wind speed also impact the power generation efficiency of wind turbines. When the wind speed is within the rated wind speed range of the wind turbine, the generator's power output increases with increasing wind speed. However, when the wind speed exceeds the rated wind speed, the generator's power output may be limited to avoid overload or damage to the equipment.

[0073] Furthermore, wind direction determines the direction of wind energy transmission, directly affecting the direction of the rotational torque of wind turbine blades. When the wind direction and the blade tilt angle are the same, the blades can achieve the maximum rotational speed, thus generating the maximum power generation efficiency. Conversely, when the wind direction is nearly perpendicular to the blades, the blades are affected by lateral forces, impacting power generation efficiency. Secondly, changes in wind direction cause a deviation between the blade angle and the wind angle, which also affects power generation efficiency. Under stable wind conditions, the wind turbine blades can maintain an optimal angle, allowing for more efficient utilization of wind energy and thus improving power generation efficiency. However, when wind direction changes significantly, the wind turbine blades need to constantly adjust their angle to adapt to different wind directions, which not only increases mechanical losses but also affects the generator's efficiency and power output.

[0074] Specifically, the power curve is used to represent the power that a wind turbine can generate at different wind speeds. The power curve of a wind turbine is usually an upward-convex curve. Ideally, when the wind speed is low, the output power is low; as the wind speed increases, the output power also increases; but when the wind speed reaches a certain value, the output power will reach a peak value, and further increases in wind speed will cause the output power to decrease.

[0075] Specifically, geographical location is typically used to describe the exact location of wind turbines, generally including data such as longitude, latitude, altitude, and regional topography. Wind speed is a key factor determining the power generation capacity of wind turbines, and its magnitude is directly affected by geographical location. Generally, wind speeds are lower in tropical and polar regions, while they are relatively higher in mid-latitude regions. This is because natural phenomena such as the Earth's rotation and atmospheric circulation produce different wind forces and directions at different latitudes. Therefore, wind power generation conditions are more favorable in mid-latitude regions, and wind turbines in these areas often achieve higher power generation. Topography is also an important factor affecting wind speed and direction. For example, complex terrain such as mountains, valleys, and coastlines can obstruct and guide airflow, creating localized wind speed variations. This topographic effect may increase wind speed in some areas, thereby increasing the power generation capacity of wind turbines; while in other areas, wind speed may decrease, leading to a reduction in power generation capacity. Altitude also affects the power generation capacity of wind turbines. Generally, wind speed increases with altitude. This is because high-altitude areas experience less ground friction, resulting in smoother airflow. Therefore, installing wind turbines at high altitudes can usually achieve higher power generation.

[0076] S102, based on the feature vectors of each wind turbine, the wind turbines are clustered to obtain multiple turbine clusters.

[0077] Clustering wind turbines involves using clustering algorithms. Clustering algorithms aim to group objects or samples in a dataset according to some similarity or feature measure, making objects within the same group as similar as possible, and objects between different groups as different as possible. Based on feature vectors, wind turbines with similar features are grouped into multiple turbine clusters through clustering.

[0078] S103, for each unit cluster, determine the number of units in the unit cluster and the model unit, and obtain the maximum power generation of the model unit in the free power generation mode; wherein, the model unit is the wind turbine unit in the unit cluster that has the shortest feature distance to the cluster center of the unit cluster.

[0079] After clustering the wind turbine units, it is necessary to determine the model units in each unit cluster, as well as the number of wind turbine units contained in each unit cluster.

[0080] Specifically, feature distance is mainly used to represent the similarity or difference between two feature vectors. There are several ways to calculate the distance between feature vectors, with Euclidean distance and cosine similarity being two commonly used methods. Euclidean distance calculates the straight-line distance between two feature vectors in multidimensional space, is sensitive to numerical magnitude, and is often used to determine numerical differences. Cosine similarity, on the other hand, measures their similarity by calculating the cosine of the angle between two feature vectors, focusing more on directional differences and being less sensitive to numerical values.

[0081] S104: For each unit cluster, the calculated power generation of the unit cluster is obtained based on the product of the number of units and the maximum power generation.

[0082] The power generation of the entire unit cluster is reflected by the power generation of the model unit. The calculated power generation of the unit cluster is obtained by multiplying the number of units in the cluster by the maximum power generation of the model unit.

[0083] S105, based on the sum of the calculated power generation of each unit cluster, obtains the maximum power generation of the target wind farm.

[0084] In this process, after obtaining the sum of the calculated power generation of each turbine cluster, the calculated power generation of each turbine cluster is added together to obtain the calculated result of the maximum power generation of the target wind farm.

[0085] In this embodiment, the model, power, wind conditions, and geographical location of each wind turbine within the wind farm are comprehensively considered. Wind turbines with similar characteristics are clustered together to form multiple turbine clusters. Then, a representative turbine is selected from each cluster to calculate the power generation of the cluster, thereby obtaining the calculated maximum generating power of the entire wind farm. By clustering the wind turbines, the selection of representative turbines is more representative, making the calculated maximum generating power based on these representative turbines more accurate and effectively improving the accuracy of the wind farm's maximum generating power calculation. This improved accuracy in maximum generating power calculation supports the subsequent specification of wind turbine power allocation and scheduling strategies within the wind farm by the control system, thereby enhancing the economic efficiency and safety of wind farm operation.

[0086] exist Figure 1 Based on the embodiments shown, the following is combined with Figure 2 The technical solution for the above-mentioned method for calculating the maximum generating power of a wind farm will be further introduced.

[0087] Figure 2 A flowchart illustrating another method for calculating the maximum generating power of a wind farm, as provided in this application embodiment, is shown below. Figure 2 In some embodiments, the method for calculating the maximum generating power of a wind farm includes the following steps:

[0088] S201, acquire the feature information of multiple wind turbines in the target wind farm, and construct the feature vector of each wind turbine based on the feature information; wherein, the feature information includes turbine model, power curve, wind condition information and geographical location information.

[0089] Specifically, let the feature vector of a wind turbine be x i Each component in the eigenvector represents a feature among the feature information, and the eigenvectors of multiple wind turbines in the target wind farm constitute the feature matrix X.

[0090] S202, randomly select any wind turbine in the target wind farm as the initial cluster center.

[0091] Before clustering the wind turbine units, it is necessary to obtain cluster centers. To begin obtaining cluster centers, any wind turbine unit in the target wind farm is randomly selected as the initial cluster center.

[0092] Specifically, in cluster analysis, cluster centers represent the central or representative position of a data cluster, summarizing the overall distribution characteristics of the data within the cluster. Cluster centers allow for a better understanding and description of the data characteristics of that cluster. The choice of cluster centers directly affects the quality of clustering. If the initial cluster centers are chosen appropriately, the clustering results are usually more accurate and stable. Conversely, if the initial cluster centers are chosen inappropriately, the clustering results may get trapped in local optima or produce erroneous clustering results.

[0093] S203, determine the current cluster center; where the initial current cluster center is the initial cluster center.

[0094] After determining the initial cluster centers, it is necessary to search for subsequent cluster centers. Therefore, before searching for subsequent cluster centers, the randomly selected initial cluster center is used as the current cluster center and serves as the starting point for the cluster center search.

[0095] S204. Based on the characteristic distance between each remaining unit and the current cluster center, determine the distribution probability of each remaining unit being selected as the next cluster center, and select the remaining unit corresponding to the maximum distribution probability as the next cluster center; where the remaining units are the other wind turbine units in the target wind farm other than the cluster center.

[0096] Specifically, based on the characteristic distance between the remaining units and the current cluster center, the distribution probability of the remaining units being selected as the next cluster center is determined, and the remaining units with the highest distribution probability are selected as the next cluster center from among the multiple remaining units.

[0097] Specifically, other wind turbine units besides the cluster center refer to all the cluster centers that have been searched and obtained during the iterative search process, including the current cluster center and the next cluster center.

[0098] Specifically, the feature distance satisfies the following formula:

[0099]

[0100] Where d(x) i ,μ k ) represents the eigenvector x of the i-th wind turbine. i The eigenvector μ of the k-th cluster center k The characteristic distance between them, x ij μ represents the j-th component in the eigenvector of the i-th wind turbine. kj Let d represent the j-th component in the eigenvector of the k-th cluster center, and d represent the number of components in the eigenvector.

[0101] Specifically, the probability distribution satisfies the following formula:

[0102]

[0103] Where P(i) represents the probability distribution of the i-th remaining unit being selected as the next cluster center, and d(x i ,μ k ) represents the feature vector x of the i-th remaining unit. i The eigenvector μ of the k-th cluster center k The feature distance between them, d(x) j ,μ k ) represents the feature vector x of the j-th remaining unit. j The eigenvector μ of the k-th cluster center k The characteristic distance between them, where n represents the number of remaining units.

[0104] As can be seen from the probability distribution formula, the remaining wind turbines that are farther away from the current cluster center have a higher probability of being selected as the next cluster center. This ensures that the selected cluster centers are as dispersed as possible, avoiding multiple cluster centers being too close together, which would cause the cluster centers to cluster into the same cluster and affect the accuracy of the wind turbine clustering results.

[0105] S205, update the current cluster center as the next cluster center, and proceed to the step of iteratively searching to determine the distribution probability of each remaining unit being selected as the next cluster center based on the feature distance between each remaining unit and the current cluster center, and select the remaining unit corresponding to the maximum distribution probability as the next cluster center, to determine multiple cluster centers.

[0106] After determining the next cluster center, this next cluster center is used as the current cluster center, and the process of searching for the next cluster center is repeated iteratively to obtain multiple cluster centers. The selection of cluster centers also affects the efficiency of clustering. Iterative search allows the initially selected cluster centers to quickly approach the actual cluster centers, enabling the subsequent clustering process to converge faster, thereby reducing the number of iterations and time overhead, and improving clustering efficiency.

[0107] Specifically, during the iterative search process, assume that K cluster centers are obtained. The number of cluster centers can be preset or obtained through existing optimization algorithms, such as the elbow rule, silhouette coefficient, and interval statistics.

[0108] S206, For each wind turbine, obtain the characteristic distance from the wind turbine to each cluster center, and assign the wind turbine to the cluster to which the cluster center with the shortest characteristic distance belongs;

[0109] After determining the cluster centers, the wind turbine units need to be clustered, and each wind turbine unit is assigned to a different cluster center to form multiple unit clusters with the cluster centers as the representative points of the clusters.

[0110] Specifically, the allocation of wind turbine units satisfies the following formula:

[0111] c i =arg min k d(x i ,μ k )

[0112] Among them, c i Let aarg min represent the i-th cluster. k d(x i ,μ k ) represents the eigenvector x of the i-th wind turbine. i The eigenvector μ of the k-th cluster center k The cluster of units whose characteristic distance is minimized.

[0113] S207, for each unit cluster, calculate the feature mean of the feature vector of each wind turbine in the cluster, and update the cluster center of the unit cluster to the feature mean;

[0114] In this process, after dividing the wind turbine clusters, the mean eigenvalue of the eigenvectors of each wind turbine in the cluster is calculated, and this mean eigenvalue is used as the cluster center of the wind turbine cluster to optimize the cluster center.

[0115] Specifically, the mean of the features satisfies the following formula:

[0116]

[0117] in, This represents the mean characteristic value of the wind turbines in the k-th turbine cluster. x represents the number of wind turbine units in the k-th unit cluster. i Let represent the feature vector of the i-th wind turbine.

[0118] S208, proceed to the step of obtaining the feature distance from each wind turbine to each cluster center for each wind turbine, and iterating the step of assigning the wind turbine to the cluster center corresponding to the shortest feature distance until convergence, thus obtaining multiple turbine clusters.

[0119] The process involves updating the cluster centers using the feature mean, then repeatedly performing the following steps for each wind turbine: obtaining the feature distance from each wind turbine to its respective cluster center, and assigning the wind turbine to the cluster corresponding to the shortest feature distance. This iterative process continues until convergence, resulting in multiple wind turbine clusters. During this iteration, the cluster centers and clusters can be continuously adjusted to optimize the cluster division, making the characteristics of wind turbines within the same cluster more similar and improving the accuracy of clustering.

[0120] S209, for each unit cluster, determine the number of units in the unit cluster and the model unit, and obtain the maximum power generation of the model unit in the free power generation mode; wherein, the model unit is the wind turbine unit in the unit cluster that has the shortest feature distance to the cluster center of the unit cluster.

[0121] S210, for each unit cluster, obtains the calculated power generation of the unit cluster based on the product of the number of units and the maximum power generation.

[0122] S211, based on the sum of the calculated power generation of each unit cluster, obtains the maximum power generation of the target wind farm.

[0123] It should be noted that the execution process of steps S209-S211 is the same as that of steps S103-S105, and will not be repeated here.

[0124] Specifically, the maximum transmittance satisfies the following formula:

[0125]

[0126] Among them, P max Indicates the maximum generating power, K represents the number of generator clusters, and m k P represents the number of units in the k-th unit cluster. k This represents the maximum power output of the model unit in the k-th unit cluster.

[0127] S212, based on the sum of the actual power generation of each wind turbine in the target wind farm, obtain the actual power generation capacity of the target wind farm.

[0128] The subsequent step involves obtaining the sum of the actual power generation of each wind turbine in the target wind farm, thus obtaining the actual power that the target wind farm can generate.

[0129] S213, calculate the cumulative root mean square error between the actual power output and the maximum power output.

[0130] Root Mean Square Error (RMSE) is a commonly used metric to measure the accuracy of a measurement model. It represents the average difference between the measured value and the actual value. The smaller the RMSE value, the better the model's measurement performance.

[0131] Specifically, the cumulative root mean square error satisfies the following formula:

[0132]

[0133] Among them, P e This represents the cumulative root mean square error, where K represents the number of unit clusters, and m k P represents the number of units in the k-th unit cluster. k This represents the maximum generating capacity of the model unit in the k-th unit cluster. This represents the actual power generation of the l-th wind turbine in the k-th turbine cluster.

[0134] S214, if the cumulative root mean square error is greater than the preset error threshold, then proceed to the step of obtaining the feature information of multiple wind turbines in the target wind farm and constructing the feature vector of each wind turbine based on the feature information.

[0135] Among them, if This indicates that the cumulative root mean square error exceeds the preset error threshold, suggesting a significant error between the calculated maximum generating power and the actual generating power. The existing unit representative cannot accurately reflect the power generation status of multiple wind turbines within the cluster, necessitating re-clustering, selection of new unit representatives, and the construction of a new cluster. Specifically, This indicates the preset error threshold.

[0136] In this embodiment, by clustering wind turbine units, the selection results of the sample units are more representative, making the maximum generating power calculated based on the sample units more accurate, and effectively improving the accuracy of the maximum generating power of the wind farm.

[0137] Figure 3 This is a schematic diagram of the structure of a wind farm maximum generating power calculation device provided in an embodiment of this application. (See attached diagram.) Figure 3 The wind farm maximum generating power calculation device includes various functional modules for implementing the aforementioned wind farm maximum generating power calculation method. Any functional module can be implemented by software and / or hardware.

[0138] In some embodiments, the wind farm maximum generating power calculation device 300 includes a feature acquisition module 301, a turbine clustering module 302, a sample selection module 303, a power calculation module 304, and a power calculation module 305. Wherein:

[0139] The feature acquisition module 301 is used to acquire feature information of multiple wind turbines in the target wind farm and construct feature vectors for each wind turbine based on the feature information; wherein, the feature information includes turbine model, power curve, wind condition information and geographical location information;

[0140] The unit clustering module 302 is used to cluster the wind turbine units according to the feature vectors of each wind turbine unit to obtain multiple unit clusters;

[0141] The template selection module 303 is used to determine the number of units in each unit cluster and the template unit for each unit cluster, and to obtain the maximum power generation of the template unit in the free power generation mode; wherein, the template unit is the wind turbine unit in the unit cluster that has the shortest feature distance to the cluster center of the unit cluster.

[0142] The power calculation module 304 is used to obtain the calculated power generation of each unit cluster based on the product of the number of units and the maximum power generation.

[0143] The power calculation module 305 is used to calculate the sum of the power generation of each unit cluster to obtain the maximum power generation of the target wind farm.

[0144] In some embodiments, the unit clustering module 302 is specifically used for:

[0145] Based on the feature vectors of each wind turbine, multiple cluster centers are determined.

[0146] For each wind turbine, the characteristic distance from the wind turbine to each cluster center is obtained, and the wind turbine is assigned to the cluster to which the cluster center with the shortest characteristic distance belongs;

[0147] For each turbine cluster, the mean eigenvector of each wind turbine in the cluster is calculated, and the cluster center of the turbine cluster is updated with the mean eigenvector.

[0148] The process then proceeds to obtaining the characteristic distances from each wind turbine to each cluster center, and assigning each wind turbine to the cluster center corresponding to the shortest characteristic distance. This process is iterated until convergence, resulting in multiple turbine clusters.

[0149] In some embodiments, the unit clustering module 302 is further configured to:

[0150] Randomly select any wind turbine in the target wind farm as the initial cluster center;

[0151] Determine the current cluster center; where the initial current cluster center is the initial cluster center;

[0152] Based on the characteristic distance between each remaining unit and the current cluster center, the distribution probability of each remaining unit being selected as the next cluster center is determined, and the remaining unit with the highest distribution probability is selected as the next cluster center; where the remaining units are the other wind turbines in the target wind farm other than the cluster center.

[0153] The current cluster center is updated as the next cluster center, and the process proceeds to the step of iteratively searching to determine the distribution probability of each remaining unit being selected as the next cluster center based on the feature distance between each remaining unit and the current cluster center, and selecting the remaining unit with the highest distribution probability as the next cluster center, to determine multiple cluster centers.

[0154] In some embodiments, the feature distance satisfies the following formula:

[0155]

[0156] Where d(x) i ,μ k ) represents the eigenvector x of the i-th wind turbine. i The eigenvector μ of the k-th cluster center k The characteristic distance between them, x ij μ represents the j-th component in the eigenvector of the i-th wind turbine. kj Let d represent the j-th component in the eigenvector of the k-th cluster center, and d represent the number of components in the eigenvector.

[0157] In some embodiments, the probability distribution satisfies the following formula:

[0158]

[0159] Where P(i) represents the probability distribution of the i-th remaining unit being selected as the next cluster center, and d(x i ,μ k ) represents the feature vector x of the i-th remaining unit. i The eigenvector μ of the k-th cluster center k The feature distance between them, d(x) j ,μ k ) represents the feature vector x of the j-th remaining unit. j The eigenvector μ of the k-th cluster center k The characteristic distance between them, where n represents the number of remaining units.

[0160] In some embodiments, the device 300 further includes an error acquisition module 306, which is specifically used for:

[0161] The actual generating power of the target wind farm is obtained by summing the actual generating power of each wind turbine in the target wind farm.

[0162] Calculate the cumulative root mean square error between the actual power output and the maximum power output;

[0163] If the cumulative root mean square error is greater than the preset error threshold, the process proceeds to the step of obtaining the feature information of multiple wind turbines in the target wind farm and constructing the feature vector of each wind turbine based on the feature information.

[0164] In some embodiments, the cumulative root mean square error satisfies the following formula:

[0165]

[0166] Among them, P e This represents the cumulative root mean square error, where K represents the number of unit clusters, and m k P represents the number of units in the k-th unit cluster. k This represents the maximum generating capacity of the model unit in the k-th unit cluster. This represents the actual power generation of the l-th wind turbine in the k-th turbine cluster.

[0167] The wind farm maximum generating power calculation device 300 provided in this application embodiment is used to execute the technical solution provided in the aforementioned wind farm maximum generating power calculation method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0168] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing elements, entirely in hardware, or partially in software via processing elements and partially in hardware. For example, the feature acquisition module can be a separate processing element, or it can be integrated into a chip within the device. Alternatively, it can be stored as program code in the device's memory, invoked and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the processor element or through software instructions.

[0169] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. (See attached diagram.) Figure 4The electronic device 400 includes: a processor 401, and a memory 402 communicatively connected to the processor 401;

[0170] Memory 402 stores instructions executed by the computer;

[0171] The processor 401 executes the computer execution instructions stored in the memory 402 to implement the technical solution of the aforementioned method for calculating the maximum generating power of a wind farm.

[0172] In the aforementioned electronic device 400, the memory 402 and the processor 401 are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines, such as bus connections. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be classified as address buses, data buses, control buses, etc., but this does not mean that there is only one bus or one type of bus. The memory 402 stores computer execution instructions that implement the aforementioned maximum generating power measurement algorithm for wind farms, including at least one software functional module that can be stored in the memory 402 in the form of software or firmware. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402.

[0173] The memory 402 includes at least one type of readable storage medium, not limited to Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 402 stores programs, which are executed by the processor 401 upon receiving execution instructions. Furthermore, the software programs and modules within the memory 402 may also include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components.

[0174] Processor 401 can be an integrated circuit chip with signal processing capabilities. The aforementioned processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or processor 401 can be any conventional processor.

[0175] The electronic device 400 is used to execute the technical solution provided in the aforementioned embodiment of the method for calculating the maximum generating power of a wind farm. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0176] This application also provides a computer-readable storage medium storing computer-executable instructions. When the processor executes the computer-executable instructions, it implements the technical solution of the aforementioned method for calculating the maximum generating power of a wind farm.

[0177] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0178] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components within the control unit of a wind farm maximum power generation calculation device.

[0179] This application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solution of the aforementioned method for calculating the maximum generating power of a wind farm.

[0180] In the above embodiments, those skilled in the art will understand that the above method embodiments can be implemented entirely or partially by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless network, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0181] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0182] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0183] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for calculating the maximum generating power of a wind farm, characterized in that, include: The system acquires feature information of multiple wind turbines within the target wind farm and constructs feature vectors for each wind turbine based on this information. The feature information includes turbine model, power curve, wind condition information, and geographical location information. The turbine model is determined by the turbine type and capacity. The wind condition information includes wind speed and direction. The power curve represents the power generated by the wind turbine at different wind speeds. The geographical location includes the longitude, latitude, altitude, and regional topography data of the wind turbine. Based on the feature vectors of each wind turbine, the wind turbines are clustered to obtain multiple turbine clusters; For each turbine cluster, the number of turbines in the cluster and the model turbine are determined, and the maximum power generation of the model turbine in the free power generation mode is obtained; wherein, the model turbine is the wind turbine in the cluster that has the shortest feature distance to the cluster center of the cluster. For each cluster of generating units, the calculated power generation of the cluster is obtained based on the product of the number of generating units and the maximum power generation. The maximum generating power of the target wind farm is obtained by summing the calculated generating power of each unit cluster. The actual generating power of the target wind farm is obtained by summing the actual generating power of each wind turbine in the target wind farm. Calculate the cumulative root mean square error between the actual transmittable power and the maximum transmittable power; If the cumulative root mean square error is greater than a preset error threshold, then proceed to the step of obtaining the feature information of multiple wind turbines in the target wind farm and constructing the feature vector of each wind turbine based on the feature information.

2. The method according to claim 1, characterized in that, Based on the feature vectors of each wind turbine, the wind turbines are clustered to obtain multiple turbine clusters, including: Based on the feature vectors of each wind turbine, multiple cluster centers are determined. For each wind turbine, the characteristic distance from the wind turbine to each cluster center is obtained, and the wind turbine is assigned to the cluster to which the cluster center corresponding to the shortest characteristic distance belongs; For each wind turbine cluster, the mean feature value of the feature vector of each wind turbine in the cluster is calculated, and the cluster center of the cluster is updated with the mean feature value. The process then proceeds to obtaining the characteristic distances from each wind turbine to each cluster center, and assigning each wind turbine to the cluster of the cluster center corresponding to the shortest characteristic distance. This process is iterated until convergence, resulting in multiple wind turbine clusters.

3. The method according to claim 2, characterized in that, Based on the feature vectors of each wind turbine, multiple cluster centers are determined, including: Randomly select any wind turbine in the target wind farm as the initial cluster center; Determine the current cluster center; wherein, the initial current cluster center is the initial cluster center; Based on the characteristic distance between each remaining unit and the current cluster center, the distribution probability of each remaining unit being selected as the next cluster center is determined, and the remaining unit corresponding to the maximum distribution probability is selected as the next cluster center; wherein, the remaining units are the other wind turbine units in the target wind farm other than the cluster center; The current cluster center is updated as the next cluster center, and the process proceeds to the step of iteratively searching to determine the distribution probability of each remaining unit being selected as the next cluster center based on the feature distance between each remaining unit and the current cluster center, and selecting the remaining unit corresponding to the maximum distribution probability as the next cluster center, in order to determine multiple cluster centers.

4. The method according to claim 3, characterized in that, The feature distance satisfies the following formula: in, Indicates the first Feature vector of a wind turbine With the The feature vector of each cluster center The characteristic distance between them Indicates the first The eigenvector of the _th wind turbine One portion, Indicates the first The eigenvector of the cluster centers is the th . One portion, This indicates the number of components in the eigenvector.

5. The method according to claim 3, characterized in that, The probability distribution satisfies the following formula: in, Indicates the first The probability distribution of the remaining units being selected as the next cluster center. Indicates the first The feature vector of the remaining units With the The feature vector of each cluster center The characteristic distance between them Indicates the first The feature vector of the remaining units With the The feature vector of each cluster center The characteristic distance between them This indicates the number of remaining generating units.

6. The method according to claim 1, characterized in that, The cumulative root mean square error satisfies the following formula: in, This represents the cumulative root mean square error. Indicates the number of unit clusters, Indicates the first The number of units in a unit cluster Indicates the first The maximum power output of the model unit in the unit cluster. Indicates the first The first in the unit cluster The actual power generation of each wind turbine unit.

7. A device for calculating the maximum generating power of a wind farm, characterized in that, include: The feature acquisition module is used to acquire feature information of multiple wind turbines within the target wind farm and construct feature vectors for each wind turbine based on the feature information. The feature information includes turbine model, power curve, wind condition information, and geographical location information. The turbine model is determined by the turbine type and capacity. The wind condition information includes wind speed and direction. The power curve represents the power generated by the wind turbine at different wind speeds. The geographical location includes the longitude, latitude, altitude, and regional topography data of the wind turbine. The unit clustering module is used to cluster the wind turbines according to the feature vectors of each wind turbine to obtain multiple unit clusters; The template selection module is used to determine the number of units and the template unit for each unit cluster, and to obtain the maximum power generation of the template unit in the free power generation mode; wherein, the template unit is the wind turbine unit in the unit cluster that has the shortest feature distance to the cluster center of the unit cluster. The power calculation module is used to obtain the calculated power generation of each unit cluster based on the product of the number of units and the maximum power generation. The power calculation module is used to obtain the maximum power output of the target wind farm based on the sum of the measured power output of each unit cluster. The error acquisition module is used to obtain the actual generating power of the target wind farm based on the sum of the actual generating power of each wind turbine in the target wind farm; calculate the root mean square error cumulative value between the actual generating power and the maximum generating power; if the root mean square error cumulative value is greater than a preset error threshold, then proceed to the step of obtaining the feature information of multiple wind turbines in the target wind farm and constructing the feature vector of each wind turbine based on the feature information.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

Images